Загрузка видео...

Не удалось загрузить видео

На главную

Impressive on every dimension! Genesis AI has announced GENE-26.5, its first robotic foundation model, aimed at achieving human-level dexterous manipulation: - Single model, shared weights, handles egg cracking, lab pipetting, bimanual Rubik's Cube, smoothie making, and wire harnessing. Most tasks: under 1 hour of task-specific data, 1x real-world speed....

TheHumanoidHub's profile picture

The Humanoid Hub

115,808 subscribers

95,894 просмотров • 5 месяцев назад •via X (Twitter)

ОбразованиеНаука и технологии
LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 0

Нет доступных комментариев

Здесь появятся комментарии из оригинального поста

Похожие видео

Imitation learning has a data scarcity problem. Introducing EgoDex from Apple, the largest and most diverse dataset of dexterous human manipulation to date — 829 hours of egocentric video + paired 3D hand poses across 194 tasks. Now on arxiv: (1/4)
0:27

Imitation learning has a data scarcity problem. Introducing EgoDex from Apple, the largest and most diverse dataset of dexterous human manipulation to date — 829 hours of egocentric video + paired 3D hand poses across 194 tasks. Now on arxiv: (1/4)

Ryan Hoque

114,330 просмотров • 1 год назад

Reward AI just came out of stealth and unveiled OM-1, a robot policy learned entirely from humans. No teleoperation, no on-robot data. One Model, Any Body. 1. Capture. A wearable 7-DoF hand (Omnibody Hand) lets people demonstrate manipulation naturally while working, cooking, or sorting. Sensors record tactile, proximity, force and hand pose at full human speed. 2. Learn. OM-1 trains on this human data alone. No teleop, no on-robot experience. Then it runs across bodies from industrial arms to humanoids, and scaling is just adding more human data. 3. Control. A high-frequency control layer, trained with RL in sim, executes those actions on any robot, holding steady through unknown loads like a stuck fridge door. The result: OM-1 picks up a brand-new task from under 30 minutes of data.
0:27

Reward AI just came out of stealth and unveiled OM-1, a robot policy learned entirely from humans. No teleoperation, no on-robot data. One Model, Any Body. 1. Capture. A wearable 7-DoF hand (Omnibody Hand) lets people demonstrate manipulation naturally while working, cooking, or sorting. Sensors record tactile, proximity, force and hand pose at full human speed. 2. Learn. OM-1 trains on this human data alone. No teleop, no on-robot experience. Then it runs across bodies from industrial arms to humanoids, and scaling is just adding more human data. 3. Control. A high-frequency control layer, trained with RL in sim, executes those actions on any robot, holding steady through unknown loads like a stuck fridge door. The result: OM-1 picks up a brand-new task from under 30 minutes of data.

The Humanoid Hub

35,672 просмотров • 21 дней назад

We are back. After one year of quiet building. Introducing GENE-26.5, our first robotic brain that takes a major step toward human-level capability. For years, robotics has struggled to learn from the world’s largest and valuable data source: Humans. Solving it means rethinking the whole stack from the ground up: - A robotics-native foundation model. - A 1:1 human-like robotic hand. - A noninvasive data collection glove for motion, force, and touch. - A simulator that turns weeks of experiments into minutes. GENE-26.5 is trained across language, vision, proprioception, tactile, and action. We designed a set of tasks to test how far we can go with this new paradigm. Fully autonomous, 1x speed, one model, same weights. (Enjoy with sound on) We are approaching the endgame for robotics. And this is just a beginning.
3:05

We are back. After one year of quiet building. Introducing GENE-26.5, our first robotic brain that takes a major step toward human-level capability. For years, robotics has struggled to learn from the world’s largest and valuable data source: Humans. Solving it means rethinking the whole stack from the ground up: - A robotics-native foundation model. - A 1:1 human-like robotic hand. - A noninvasive data collection glove for motion, force, and touch. - A simulator that turns weeks of experiments into minutes. GENE-26.5 is trained across language, vision, proprioception, tactile, and action. We designed a set of tasks to test how far we can go with this new paradigm. Fully autonomous, 1x speed, one model, same weights. (Enjoy with sound on) We are approaching the endgame for robotics. And this is just a beginning.

Genesis AI

2,745,306 просмотров • 5 месяцев назад

Mimic Robotics released a full-stack dexterity platform: the mimic hand M1 + umimic (U1) wearable. They keep human hand morphology consistent across the entire data-model-dexterous hand-manipulation pipeline--from video pre-training to wearable demos and robot deployment. This avoids cross-embodiment gaps and captures the essence of upper-limb intelligence. M1: Tendon-driven (15 active DoF), highly backdrivable ( 25kg grasp, industrial-grade, Swiss-made. U1 lets humans teach the robot naturally with their own hands--1:1 kinematics and sensing match, no latency or retargeting, enabling higher-quality and more scalable data. Looking forward to its performance at the customer site.
0:52

Mimic Robotics released a full-stack dexterity platform: the mimic hand M1 + umimic (U1) wearable. They keep human hand morphology consistent across the entire data-model-dexterous hand-manipulation pipeline--from video pre-training to wearable demos and robot deployment. This avoids cross-embodiment gaps and captures the essence of upper-limb intelligence. M1: Tendon-driven (15 active DoF), highly backdrivable ( 25kg grasp, industrial-grade, Swiss-made. U1 lets humans teach the robot naturally with their own hands--1:1 kinematics and sensing match, no latency or retargeting, enabling higher-quality and more scalable data. Looking forward to its performance at the customer site.

CyberRobo

26,160 просмотров • 2 месяцев назад

Are you kidding me??? It grasps multiple objects with different ways, all at once with… a single hand??? No pauses. 1x speed. GENE-26.5 is Genesis AI’s robotics-native multimodal foundation model. It’s trained on 200,000+ hours of real human hand data (motion, force, touch) and runs on a 54-DoF bimanual system: Scaling that human data 4x lifted real-robot success rates from 16.6% to 65.6% on long-horizon dexterous tasks!! Same model weights, zero fine-tuning for this exact sequence. You know those tiny coordinated movements you do without thinking…? Robots couldn’t reliably do that before. Now they can. Today. This is the video you’ll send to my friends, outside of our bubble, when they say “robots are still just demos.” Congrats to the entire team around Zhou Xian! Credit: Seen at Zu Wang (Zu) Genesis official announcement for the full story + longer demo: ——— Weekly robotics and AI insights. Subscribe free:
0:20

Are you kidding me??? It grasps multiple objects with different ways, all at once with… a single hand??? No pauses. 1x speed. GENE-26.5 is Genesis AI’s robotics-native multimodal foundation model. It’s trained on 200,000+ hours of real human hand data (motion, force, touch) and runs on a 54-DoF bimanual system: Scaling that human data 4x lifted real-robot success rates from 16.6% to 65.6% on long-horizon dexterous tasks!! Same model weights, zero fine-tuning for this exact sequence. You know those tiny coordinated movements you do without thinking…? Robots couldn’t reliably do that before. Now they can. Today. This is the video you’ll send to my friends, outside of our bubble, when they say “robots are still just demos.” Congrats to the entire team around Zhou Xian! Credit: Seen at Zu Wang (Zu) Genesis official announcement for the full story + longer demo: ——— Weekly robotics and AI insights. Subscribe free:

Ilir Aliu

204,737 просмотров • 5 месяцев назад

TARS has made some big announcements at ICRA 2026. DexHand - A dexterous hand with 1:1 replication of human metacarpal and finger structure, multi-axis thumb opposition - Quasi-direct-drive + backdrivable joints, 21 degrees of freedom - All 26 ASL letter signs reproduced at high precision -0.05mm fingertip tactile sensing - Data. Model. Hand. Fused into one embodied AI-native dexterous hand. OmniVTA with TacForeSight A visuo-tactile world model for general-use, paired with TacForeSight, a force-guided technology that not only allows robots to understand contact but also enables them to predict contact before it happens. - Semantic touch ("slippery," "rough," "soft," "hard") enabling texture-based material cognition. - Operates inside a real-time closed loop - Contact state prediction and reaction at the microsecond scale, faster than human AWE 3.0 - Claimed to be the world's leading general-purpose embodied foundation model for real-world work - A1 robot packing demo as the showcase: long-horizon, bimanual, with autonomous error recovery and end-to-end imitation learning - Set a Guinness World Record in March 2026 for "Most sub-millimeter wire harness assembled by a robot in one hour" - SenseHub data acquisition suite captures human experience data to train AWE 3.0
0:40

TARS has made some big announcements at ICRA 2026. DexHand - A dexterous hand with 1:1 replication of human metacarpal and finger structure, multi-axis thumb opposition - Quasi-direct-drive + backdrivable joints, 21 degrees of freedom - All 26 ASL letter signs reproduced at high precision -0.05mm fingertip tactile sensing - Data. Model. Hand. Fused into one embodied AI-native dexterous hand. OmniVTA with TacForeSight A visuo-tactile world model for general-use, paired with TacForeSight, a force-guided technology that not only allows robots to understand contact but also enables them to predict contact before it happens. - Semantic touch ("slippery," "rough," "soft," "hard") enabling texture-based material cognition. - Operates inside a real-time closed loop - Contact state prediction and reaction at the microsecond scale, faster than human AWE 3.0 - Claimed to be the world's leading general-purpose embodied foundation model for real-world work - A1 robot packing demo as the showcase: long-horizon, bimanual, with autonomous error recovery and end-to-end imitation learning - Set a Guinness World Record in March 2026 for "Most sub-millimeter wire harness assembled by a robot in one hour" - SenseHub data acquisition suite captures human experience data to train AWE 3.0

The Humanoid Hub

11,322 просмотров • 3 месяцев назад

How well do egocentric human videos scale? Apparently, really well. Dyna Robotics has introduced Dyna-2, a world-action model (WAM) pre-trained on more than 1 million hours of real egocentric human video. It learns by jointly predicting the next video frames and the actions, and that video prediction (world modeling) is what carries learning from humans to robots. • More human video predictably improves action prediction. • Task accuracy improves across embodiments (bimanual arms and a humanoid) with zero robot data in pre-training. • Post-trained on just a few hours of robot data, mean task performance rose 20% to 53% as human pre-training scaled 1k to 1M hours. WAM vs VLA, matched apple-to-apple: the WAM hit 1.55x the VLA's success rate and won 65% of head-to-heads. Deployed zero-shot at unseen customer sites, it passed 87% vs the VLA's 46%.
0:28

How well do egocentric human videos scale? Apparently, really well. Dyna Robotics has introduced Dyna-2, a world-action model (WAM) pre-trained on more than 1 million hours of real egocentric human video. It learns by jointly predicting the next video frames and the actions, and that video prediction (world modeling) is what carries learning from humans to robots. • More human video predictably improves action prediction. • Task accuracy improves across embodiments (bimanual arms and a humanoid) with zero robot data in pre-training. • Post-trained on just a few hours of robot data, mean task performance rose 20% to 53% as human pre-training scaled 1k to 1M hours. WAM vs VLA, matched apple-to-apple: the WAM hit 1.55x the VLA's success rate and won 65% of head-to-heads. Deployed zero-shot at unseen customer sites, it passed 87% vs the VLA's 46%.

The Humanoid Hub

15,970 просмотров • 1 месяц назад

1/🧠Humans are the best robot data source — but video alone misses one thing: force. 2/🙁Tactile gloves capture force — but they're costly and block the real touch manipulation depends on. 3/💪Maybe the future of touch lives on your wrist: surface EMG reads the muscles that cause force — tactile sensing without ever touching a tactile sensor. 4/🔥Want a fully open-source framework — hardware + software — to train your own force-aware learn-from-human-data robot policy? 🚀We introduce ForceBand: Learning Forceful Manipulation with sEMG -- bring force into human videos with sEMG, for force-aware manipulation ⬇️ ✦ Zero-Shot Human-to-Robot Transfer ✦ Force Beyond Vision ✦ Free-Hand Force Sensing ✦ Collect by Anyone, Anytime, Anywhere ✦ Deploy on Any Robot, Any Camera, Any Environment ✦ Open-Source & Low-Cost & Easy-to-Implement Let's squeeze every bit of signal out of human data, and let robots feel the force! 🌐 Website: 📄 Paper: 💻 Code: 🎥 Video: 🧵 1/n
1:48

1/🧠Humans are the best robot data source — but video alone misses one thing: force. 2/🙁Tactile gloves capture force — but they're costly and block the real touch manipulation depends on. 3/💪Maybe the future of touch lives on your wrist: surface EMG reads the muscles that cause force — tactile sensing without ever touching a tactile sensor. 4/🔥Want a fully open-source framework — hardware + software — to train your own force-aware learn-from-human-data robot policy? 🚀We introduce ForceBand: Learning Forceful Manipulation with sEMG -- bring force into human videos with sEMG, for force-aware manipulation ⬇️ ✦ Zero-Shot Human-to-Robot Transfer ✦ Force Beyond Vision ✦ Free-Hand Force Sensing ✦ Collect by Anyone, Anytime, Anywhere ✦ Deploy on Any Robot, Any Camera, Any Environment ✦ Open-Source & Low-Cost & Easy-to-Implement Let's squeeze every bit of signal out of human data, and let robots feel the force! 🌐 Website: 📄 Paper: 💻 Code: 🎥 Video: 🧵 1/n

Zhi (Leo) Wang✈️IROS2026

52,852 просмотров • 3 месяцев назад

Jason Ma reveals the first true scaling law in robotics: robots trained on 1 million hours of first-person human video predictably get better without ever seeing robot data "Yesterday we announced our new flagship robot foundation model called Dyna-2. It's very significant for the entire field for many different reasons. First of all, it's the first robot foundation model trained on at least one million hours of data. That in itself is a very challenging infrastructure challenge." "What we demonstrated is that even if the one million hours of data is entirely first-person video of humans doing manipulation tasks, we actually see scaling law for transferring to robot embodiments that the model has never seen before." "By training on more human data, we actually see predictable performance improvement on robots. That's a big deal because the biggest challenge facing robot foundation models is that we don't have enough data." "Unlike language models, there are just not enough robotics data out there, and it's very difficult to collect these robot data. Only by passively observing humans doing things can we scale this kind of data, and this is the first time we showed there is a lot of improvement that can transfer." Jason Ma Dyna Robotics
1:14

Jason Ma reveals the first true scaling law in robotics: robots trained on 1 million hours of first-person human video predictably get better without ever seeing robot data "Yesterday we announced our new flagship robot foundation model called Dyna-2. It's very significant for the entire field for many different reasons. First of all, it's the first robot foundation model trained on at least one million hours of data. That in itself is a very challenging infrastructure challenge." "What we demonstrated is that even if the one million hours of data is entirely first-person video of humans doing manipulation tasks, we actually see scaling law for transferring to robot embodiments that the model has never seen before." "By training on more human data, we actually see predictable performance improvement on robots. That's a big deal because the biggest challenge facing robot foundation models is that we don't have enough data." "Unlike language models, there are just not enough robotics data out there, and it's very difficult to collect these robot data. Only by passively observing humans doing things can we scale this kind of data, and this is the first time we showed there is a lot of improvement that can transfer." Jason Ma Dyna Robotics

MTS

17,740 просмотров • 1 месяц назад

NVIDIA just announced EgoScale 🤖🧠 NVIDIA Research has uncovered a log-linear scaling law for robot dexterity by pretraining VLA models on over 20,000 hours of egocentric human video This massive dataset is 20 times larger than previous efforts and proves that robot intelligence follows a predictable path: the more human data, the lower the loss The secret is a simple recipe combining large-scale human pretraining with a small amount of aligned human-robot mid-training to bridge the gap In testing, this method boosted the average success rate by 54% on a 22-DoF robotic hand compared to policies built without pretraining EgoScale also enables one-shot task adaptation and works across different hardware, suggesting that human motion is a universal motor prior for robots Website: Paper: Source: NVIDIA Research #Robot #Humanoid #Robotics #AI #EmbodiedAI #PhysicalAI #NVIDIA #EgoScale #GR00T
1:25

NVIDIA just announced EgoScale 🤖🧠 NVIDIA Research has uncovered a log-linear scaling law for robot dexterity by pretraining VLA models on over 20,000 hours of egocentric human video This massive dataset is 20 times larger than previous efforts and proves that robot intelligence follows a predictable path: the more human data, the lower the loss The secret is a simple recipe combining large-scale human pretraining with a small amount of aligned human-robot mid-training to bridge the gap In testing, this method boosted the average success rate by 54% on a 22-DoF robotic hand compared to policies built without pretraining EgoScale also enables one-shot task adaptation and works across different hardware, suggesting that human motion is a universal motor prior for robots Website: Paper: Source: NVIDIA Research #Robot #Humanoid #Robotics #AI #EmbodiedAI #PhysicalAI #NVIDIA #EgoScale #GR00T

RoboHub🤖

43,752 просмотров • 7 месяцев назад

We trained a humanoid with 22-DoF dexterous hands to assemble model cars, operate syringes, sort poker cards, fold/roll shirts, all learned primarily from 20,000+ hours of egocentric human video with no robot in the loop. Humans are the most scalable embodiment on the planet. We discovered a near-perfect log-linear scaling law (R² = 0.998) between human video volume and action prediction loss, and this loss directly predicts real-robot success rate. Humanoid robots will be the end game, because they are the practical form factor with minimal embodiment gap from humans. Call it the Bitter Lesson of robot hardware: the kinematic similarity lets us simply retarget human finger motion onto dexterous robot hand joints. No learned embeddings, no fancy transfer algorithms needed. Relative wrist motion + retargeted 22-DoF finger actions serve as a unified action space that carries through from pre-training to robot execution. Our recipe is called "EgoScale": - Pre-train GR00T N1.5 on 20K hours of human video, mid-train with only 4 hours (!) of robot play data with Sharpa hands. 54% gains over training from scratch across 5 highly dexterous tasks. - Most surprising result: a *single* teleop demo is sufficient to learn a never-before-seen task. Our recipe enables extreme data efficiency. - Although we pre-train in 22-DoF hand joint space, the policy transfers to a Unitree G1 with 7-DoF tri-finger hands. 30%+ gains over training on G1 data alone. The scalable path to robot dexterity was never more robots. It was always us. Deep dives in thread:
1:17

We trained a humanoid with 22-DoF dexterous hands to assemble model cars, operate syringes, sort poker cards, fold/roll shirts, all learned primarily from 20,000+ hours of egocentric human video with no robot in the loop. Humans are the most scalable embodiment on the planet. We discovered a near-perfect log-linear scaling law (R² = 0.998) between human video volume and action prediction loss, and this loss directly predicts real-robot success rate. Humanoid robots will be the end game, because they are the practical form factor with minimal embodiment gap from humans. Call it the Bitter Lesson of robot hardware: the kinematic similarity lets us simply retarget human finger motion onto dexterous robot hand joints. No learned embeddings, no fancy transfer algorithms needed. Relative wrist motion + retargeted 22-DoF finger actions serve as a unified action space that carries through from pre-training to robot execution. Our recipe is called "EgoScale": - Pre-train GR00T N1.5 on 20K hours of human video, mid-train with only 4 hours (!) of robot play data with Sharpa hands. 54% gains over training from scratch across 5 highly dexterous tasks. - Most surprising result: a *single* teleop demo is sufficient to learn a never-before-seen task. Our recipe enables extreme data efficiency. - Although we pre-train in 22-DoF hand joint space, the policy transfers to a Unitree G1 with 7-DoF tri-finger hands. 30%+ gains over training on G1 data alone. The scalable path to robot dexterity was never more robots. It was always us. Deep dives in thread:

Jim Fan

301,976 просмотров • 7 месяцев назад

Sharing a copy of my ICRA'26 keynote talk from three months ago. 3 key messages: 1. Building a human-like machine, a dream that has fascinated humankind for centuries, is rapidly becoming a reality. 2. Human data is, by far, the most scalable source of training data to fuel robot foundation models. 3. World models are a "data sponge" that can absorb massive amounts of multimodal data for policy generalization. Video: Slides: The talk brought together our work over the past year: GR00T, EgoScale, SONIC, WAM, and more. Here’s the same demo I showed on stage: Our (now old!) model learning to assemble the YCB airplane with zero teleop data. We've made incredible progress since then. What's coming next? 🚀
1:17

Sharing a copy of my ICRA'26 keynote talk from three months ago. 3 key messages: 1. Building a human-like machine, a dream that has fascinated humankind for centuries, is rapidly becoming a reality. 2. Human data is, by far, the most scalable source of training data to fuel robot foundation models. 3. World models are a "data sponge" that can absorb massive amounts of multimodal data for policy generalization. Video: Slides: The talk brought together our work over the past year: GR00T, EgoScale, SONIC, WAM, and more. Here’s the same demo I showed on stage: Our (now old!) model learning to assemble the YCB airplane with zero teleop data. We've made incredible progress since then. What's coming next? 🚀

Yuke Zhu

10,591 просмотров • 7 дней назад

JUST IN: Dyna Robotics just published one of the most important research papers in robotics this year. It could fundamentally change how robot foundation models are trained. A scaling law that transfers from human video to robot performance. Dyna-2 is out and it's 🔥 Here's what that means in plain terms. Dyna-2 was pre-trained on ONE MILLION hours of egocentric human video, 170 years of continuous human experience, cooking, folding, assembling, cleaning. And as that human data scaled, robot performance improved. Predictably. Monotonically. Across 39 tasks on two different robot embodiments the model had never seen. → 1,000 hours pre-training → 20% normalised task performance → 10,000 hours → 28% → 100,000 hours → 45% → 1,000,000 hours → 53% Human video exists at effectively unlimited scale. Every cook, every factory worker, every craftsperson wearing a camera is generating training data for future robots. But the finding that stunned even the researchers, world modeling is what makes the transfer work. A model trained to predict future video AND actions massively outperforms one trained on actions alone. Video is the new scaling axis for robotics. One more jaw-dropping data point. 13 minutes of teleoperation data was enough to fine-tune Dyna-2 to open a bottle cap using two five-fingered robot hands. The robots are coming, and they're learning from us directly :D Read more here: Congrats Jason Ma and team! ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →
1:35

JUST IN: Dyna Robotics just published one of the most important research papers in robotics this year. It could fundamentally change how robot foundation models are trained. A scaling law that transfers from human video to robot performance. Dyna-2 is out and it's 🔥 Here's what that means in plain terms. Dyna-2 was pre-trained on ONE MILLION hours of egocentric human video, 170 years of continuous human experience, cooking, folding, assembling, cleaning. And as that human data scaled, robot performance improved. Predictably. Monotonically. Across 39 tasks on two different robot embodiments the model had never seen. → 1,000 hours pre-training → 20% normalised task performance → 10,000 hours → 28% → 100,000 hours → 45% → 1,000,000 hours → 53% Human video exists at effectively unlimited scale. Every cook, every factory worker, every craftsperson wearing a camera is generating training data for future robots. But the finding that stunned even the researchers, world modeling is what makes the transfer work. A model trained to predict future video AND actions massively outperforms one trained on actions alone. Video is the new scaling axis for robotics. One more jaw-dropping data point. 13 minutes of teleoperation data was enough to fine-tune Dyna-2 to open a bottle cap using two five-fingered robot hands. The robots are coming, and they're learning from us directly :D Read more here: Congrats Jason Ma and team! ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →

Lukas Ziegler

23,681 просмотров • 1 месяц назад

Figure announces Project Go-Big: Internet-Scale Humanoid Pretraining and Direct Human-to-Robot Transfer The company has achieved a new milestone for the Helix AI model: after training exclusively on egocentric human data, Figure robots can now navigate real-world spaces from natural language commands such as “Go water the plants.” This also enabled a unified Helix model that can output both manipulation and navigation commands to the continuous control system. This ties into the Brookfield partnership that they announced yesterday. Brookfield is a global asset manager overseeing $1 trillion in assets, including 100,000 residential units, 500M square feet of commercial office space, and 160M square feet of logistics space. Using human video capture in a variety of Brookfield environments, Figure will amass critical pretraining data at scale, allowing them to explore the full potential of internet-scale embodied datasets for locomotion and manipulation.
1:03

Figure announces Project Go-Big: Internet-Scale Humanoid Pretraining and Direct Human-to-Robot Transfer The company has achieved a new milestone for the Helix AI model: after training exclusively on egocentric human data, Figure robots can now navigate real-world spaces from natural language commands such as “Go water the plants.” This also enabled a unified Helix model that can output both manipulation and navigation commands to the continuous control system. This ties into the Brookfield partnership that they announced yesterday. Brookfield is a global asset manager overseeing $1 trillion in assets, including 100,000 residential units, 500M square feet of commercial office space, and 160M square feet of logistics space. Using human video capture in a variety of Brookfield environments, Figure will amass critical pretraining data at scale, allowing them to explore the full potential of internet-scale embodied datasets for locomotion and manipulation.

The Humanoid Hub

32,953 просмотров • 1 год назад

Exciting updates on Project GR00T! We discover a systematic way to scale up robot data, tackling the most painful pain point in robotics. The idea is simple: human collects demonstration on a real robot, and we multiply that data 1000x or more in simulation. Let’s break it down: 1. We use Apple Vision Pro (yes!!) to give the human operator first person control of the humanoid. Vision Pro parses human hand pose and retargets the motion to the robot hand, all in real time. From the human’s point of view, they are immersed in another body like the Avatar. Teleoperation is slow and time-consuming, but we can afford to collect a small amount of data. 2. We use RoboCasa, a generative simulation framework, to multiply the demonstration data by varying the visual appearance and layout of the environment. In Jensen’s keynote video below, the humanoid is now placing the cup in hundreds of kitchens with a huge diversity of textures, furniture, and object placement. We only have 1 physical kitchen at the GEAR Lab in NVIDIA HQ, but we can conjure up infinite ones in simulation. 3. Finally, we apply MimicGen, a technique to multiply the above data even more by varying the *motion* of the robot. MimicGen generates vast number of new action trajectories based on the original human data, and filters out failed ones (e.g. those that drop the cup) to form a much larger dataset. To sum up, given 1 human trajectory with Vision Pro -> RoboCasa produces N (varying visuals) -> MimicGen further augments to NxM (varying motions). This is the way to trade compute for expensive human data by GPU-accelerated simulation. A while ago, I mentioned that teleoperation is fundamentally not scalable, because we are always limited by 24 hrs/robot/day in the world of atoms. Our new GR00T synthetic data pipeline breaks this barrier in the world of bits. Scaling has been so much fun for LLMs, and it's finally our turn to have fun in robotics! We are building tools to enable everyone in the ecosystem to scale up with us. Links in thread:
1:21

Exciting updates on Project GR00T! We discover a systematic way to scale up robot data, tackling the most painful pain point in robotics. The idea is simple: human collects demonstration on a real robot, and we multiply that data 1000x or more in simulation. Let’s break it down: 1. We use Apple Vision Pro (yes!!) to give the human operator first person control of the humanoid. Vision Pro parses human hand pose and retargets the motion to the robot hand, all in real time. From the human’s point of view, they are immersed in another body like the Avatar. Teleoperation is slow and time-consuming, but we can afford to collect a small amount of data. 2. We use RoboCasa, a generative simulation framework, to multiply the demonstration data by varying the visual appearance and layout of the environment. In Jensen’s keynote video below, the humanoid is now placing the cup in hundreds of kitchens with a huge diversity of textures, furniture, and object placement. We only have 1 physical kitchen at the GEAR Lab in NVIDIA HQ, but we can conjure up infinite ones in simulation. 3. Finally, we apply MimicGen, a technique to multiply the above data even more by varying the *motion* of the robot. MimicGen generates vast number of new action trajectories based on the original human data, and filters out failed ones (e.g. those that drop the cup) to form a much larger dataset. To sum up, given 1 human trajectory with Vision Pro -> RoboCasa produces N (varying visuals) -> MimicGen further augments to NxM (varying motions). This is the way to trade compute for expensive human data by GPU-accelerated simulation. A while ago, I mentioned that teleoperation is fundamentally not scalable, because we are always limited by 24 hrs/robot/day in the world of atoms. Our new GR00T synthetic data pipeline breaks this barrier in the world of bits. Scaling has been so much fun for LLMs, and it's finally our turn to have fun in robotics! We are building tools to enable everyone in the ecosystem to scale up with us. Links in thread:

Jim Fan

364,670 просмотров • 2 лет назад

Figure just stacked the two halves of the Physical AI bottleneck a week apart. First Index: a creator network collecting real-world task video at roughly half an hour of uploads every second, across homes and workplaces in 100+ countries. That is the long-tail data you do not get from a lab teleop setup. Then Nscale: $3.5B of compute to start, intent past $6B, up to 100,000 NVIDIA Vera Rubin GPUs. Brett Adcock said they are largely constrained by data and compute. Index is the data bet. Nscale is the compute bet. Figure's own writeup says the quiet part: data alone cannot solve this. My take: Compute is a prerequisite. Collecting more data is critical. But finding the 1% of data that actually teaches the model is what compounds. Search and curation, not just capture. That's the problem we are focused on solving at Foxglove.
1:15

Figure just stacked the two halves of the Physical AI bottleneck a week apart. First Index: a creator network collecting real-world task video at roughly half an hour of uploads every second, across homes and workplaces in 100+ countries. That is the long-tail data you do not get from a lab teleop setup. Then Nscale: $3.5B of compute to start, intent past $6B, up to 100,000 NVIDIA Vera Rubin GPUs. Brett Adcock said they are largely constrained by data and compute. Index is the data bet. Nscale is the compute bet. Figure's own writeup says the quiet part: data alone cannot solve this. My take: Compute is a prerequisite. Collecting more data is critical. But finding the 1% of data that actually teaches the model is what compounds. Search and curation, not just capture. That's the problem we are focused on solving at Foxglove.

Adrian Macneil

104,588 просмотров • 28 дней назад

Robotics has a massive, silent bottleneck. It isn’t just data collection—it’s the brutal 1x speed of the physical world. Genesis AI Genesis AI just unveiled Genesis World 1.0, and they are attempting to turn the notorious Sim2Real gap into a pure compute problem. Evaluating a robotics foundation model across edge cases usually means hundreds of hours of physical lab testing. With Genesis World 1.0, what traditionally takes nearly a week of continuous, real-world operation is being compressed into 30 minutes in simulation. What makes this different from just dropping a robot model into an off-the-shelf game engine? 1️⃣ Nyx Renderer: A custom, real-time path-traced engine rendering noise-free 1080p frames in under 4ms. Game engines use rasterization tricks that confuse AI; Nyx uses physically accurate multi-bounce lighting so the model's "eyes" see exactly what real sensors see. 2️⃣ Quadrants Compiler: A custom Python-to-GPU compiler to run heavily parallelized multi-physics simulations (rigid bodies, fluids, deformables) natively across architectures. 3️⃣ Evaluation First: They aren't rushing to train on synthetic data. They are using this purely for closed-loop evaluation to perfect the physics first, currently claiming an impressive 89% correlation with real-world hardware tests. If the industry can accurately evaluate models in simulation without the physical world bottleneck, humanoid development stops moving at wall-clock time and starts scaling with compute.
1:36

Robotics has a massive, silent bottleneck. It isn’t just data collection—it’s the brutal 1x speed of the physical world. Genesis AI Genesis AI just unveiled Genesis World 1.0, and they are attempting to turn the notorious Sim2Real gap into a pure compute problem. Evaluating a robotics foundation model across edge cases usually means hundreds of hours of physical lab testing. With Genesis World 1.0, what traditionally takes nearly a week of continuous, real-world operation is being compressed into 30 minutes in simulation. What makes this different from just dropping a robot model into an off-the-shelf game engine? 1️⃣ Nyx Renderer: A custom, real-time path-traced engine rendering noise-free 1080p frames in under 4ms. Game engines use rasterization tricks that confuse AI; Nyx uses physically accurate multi-bounce lighting so the model's "eyes" see exactly what real sensors see. 2️⃣ Quadrants Compiler: A custom Python-to-GPU compiler to run heavily parallelized multi-physics simulations (rigid bodies, fluids, deformables) natively across architectures. 3️⃣ Evaluation First: They aren't rushing to train on synthetic data. They are using this purely for closed-loop evaluation to perfect the physics first, currently claiming an impressive 89% correlation with real-world hardware tests. If the industry can accurately evaluate models in simulation without the physical world bottleneck, humanoid development stops moving at wall-clock time and starts scaling with compute.

Humanoids daily

17,302 просмотров • 4 месяцев назад

We are back again :) After three weeks of quiet building. Introducing Genesis World 1.0, our latest simulation platform, the second release in our full-stack suite. Open-sourced. Robotics is still bottlenecked by the 1× speed of the physical world. Every model, checkpoint, and data recipe eventually needs to be tested on physical hardware, slowly, expensively, and with limited coverage. One hour in reality can become 100 days in simulation. That is how robotics model iteration moves from a wall-clock bottleneck to a compute problem. To make this work, simulation has to be both fast and trustworthy. Over the past year, we rebuilt the entire stack: a GPU-accelerated cross-platform compiler, penetration-free multi-physics contact solvers, unified rigid and deformable physics, and a photo-realistic renderer purpose-built for physical AI applications. We built Nyx, a high-performance path-traced rendering engine for robotics application. Genesis World 1.0 achieves near realtime performance with our latest development for penetration-free IPC solver, supporting various types of deformables beyond rigid bodies. It supports contact-rich, dexterous manipulation simulation across different embodiments: unitree, sharpa, wuji, genesis hand and various types of grippers. Under the hood is Quadrants, our effort in pushing forward cross-platform GPU-accelerated computation. Quadrants started as a fork of Taichi, and we rebuilt most of the critical parts for optimizing simulation workloads, giving 10x faster launch time and up to 4.6x runtime performance compared to the initial Genesis release. Together, they bring us to an unprecedentedly low sim-to-real gap, enabling zero-shot real-to-sim model evaluation and much faster iteration of GENE. All available today. Genesis World 1.0: Quadrants: Nyx:
2:51

We are back again :) After three weeks of quiet building. Introducing Genesis World 1.0, our latest simulation platform, the second release in our full-stack suite. Open-sourced. Robotics is still bottlenecked by the 1× speed of the physical world. Every model, checkpoint, and data recipe eventually needs to be tested on physical hardware, slowly, expensively, and with limited coverage. One hour in reality can become 100 days in simulation. That is how robotics model iteration moves from a wall-clock bottleneck to a compute problem. To make this work, simulation has to be both fast and trustworthy. Over the past year, we rebuilt the entire stack: a GPU-accelerated cross-platform compiler, penetration-free multi-physics contact solvers, unified rigid and deformable physics, and a photo-realistic renderer purpose-built for physical AI applications. We built Nyx, a high-performance path-traced rendering engine for robotics application. Genesis World 1.0 achieves near realtime performance with our latest development for penetration-free IPC solver, supporting various types of deformables beyond rigid bodies. It supports contact-rich, dexterous manipulation simulation across different embodiments: unitree, sharpa, wuji, genesis hand and various types of grippers. Under the hood is Quadrants, our effort in pushing forward cross-platform GPU-accelerated computation. Quadrants started as a fork of Taichi, and we rebuilt most of the critical parts for optimizing simulation workloads, giving 10x faster launch time and up to 4.6x runtime performance compared to the initial Genesis release. Together, they bring us to an unprecedentedly low sim-to-real gap, enabling zero-shot real-to-sim model evaluation and much faster iteration of GENE. All available today. Genesis World 1.0: Quadrants: Nyx:

Genesis AI

324,061 просмотров • 4 месяцев назад

Studies have shown ChatGPT outperforms human annotators for Structured Data by about 25% and costs 30x less. 1 In just 2 months, miners on SN33 running ChatGPT without optimization can’t survive. Today we announce SN33 is now ReadyAI to fully align with our mission 👇 SN33 is building a more performant and significantly cheaper alternative to Scale AI Today structured data is performed primarily by human annotation services like Amazon’s Mechanical Turk and Scale AI It is now more important than ever for every business and individual to make their data AI Ready. However, taking unstructured data and making it Structured Data using today’s tools is extremely costly. SN33 revolutionizes this process, unlocking immense opportunities for commercialization. We lay out the vision for it in this detailed blog post: Validators TODAY can monetize access to this structured data pipeline independently, but we’re streamlining this process, launching a frontend soon that any validator can opt into to provide bandwidth. We've received great feedback from the community, recognizing that what we're building goes far beyond Conversational AI. Building the world's largest annotated conversational dataset (which we've already accomplished) is just one of countless real-world applications for SN33's Structured Data pipeline. We're building a decentralized Scale AI, offering a full suite of Structured Data commodities—from text metadata tagging (available today) to fully customizable queries for company-specific data annotation use cases and image metadata tagging coming soon 👀. Thanks for all the feedback! It has been invaluable so keep bringing it to us! 🙏$TAO Openτensor Foundaτion 1 “ChatGPT Outperforms Crowd-Workers for Text-Annotation Tasks” shows “The zero-shot accuracy of ChatGPT exceeds that of crowd-workers by about 25 percentage points on average [...] Moreover, the per-annotation cost of ChatGPT is less than $0.003—about thirty times cheaper than MTurk”
1:16

Studies have shown ChatGPT outperforms human annotators for Structured Data by about 25% and costs 30x less. 1 In just 2 months, miners on SN33 running ChatGPT without optimization can’t survive. Today we announce SN33 is now ReadyAI to fully align with our mission 👇 SN33 is building a more performant and significantly cheaper alternative to Scale AI Today structured data is performed primarily by human annotation services like Amazon’s Mechanical Turk and Scale AI It is now more important than ever for every business and individual to make their data AI Ready. However, taking unstructured data and making it Structured Data using today’s tools is extremely costly. SN33 revolutionizes this process, unlocking immense opportunities for commercialization. We lay out the vision for it in this detailed blog post: Validators TODAY can monetize access to this structured data pipeline independently, but we’re streamlining this process, launching a frontend soon that any validator can opt into to provide bandwidth. We've received great feedback from the community, recognizing that what we're building goes far beyond Conversational AI. Building the world's largest annotated conversational dataset (which we've already accomplished) is just one of countless real-world applications for SN33's Structured Data pipeline. We're building a decentralized Scale AI, offering a full suite of Structured Data commodities—from text metadata tagging (available today) to fully customizable queries for company-specific data annotation use cases and image metadata tagging coming soon 👀. Thanks for all the feedback! It has been invaluable so keep bringing it to us! 🙏$TAO Openτensor Foundaτion 1 “ChatGPT Outperforms Crowd-Workers for Text-Annotation Tasks” shows “The zero-shot accuracy of ChatGPT exceeds that of crowd-workers by about 25 percentage points on average [...] Moreover, the per-annotation cost of ChatGPT is less than $0.003—about thirty times cheaper than MTurk”

David Fields

13,656 просмотров • 2 лет назад

Excited to announce GR00T N1, the world’s first open foundation model for humanoid robots! We are on a mission to democratize Physical AI. The power of general robot brain, in the palm of your hand - with only 2B parameters, N1 learns from the most diverse physical action dataset ever compiled and punches above its weight: - Real humanoid teleoperation data. - Large-scale simulation data: we are open-sourcing 300K+ trajectories! - Neural trajectories: we apply SOTA video generation models to “hallucinate” new synthetic data that features accurate physics in pixels. Using Jensen’s words, “systematically infinite data”! - Latent actions: we develop novel algorithms to extract action tokens from in-the-wild human videos and neural generated videos. GR00T N1 is a single end-to-end neural net, from photons to actions: - Vision-Language Model (System 2) that interprets the physical world through vision and language instructions, enabling robots to reason about their environment and instructions, and plan the right actions. - Diffusion Transformer (System 1) that “renders” smooth and precise motor actions at 120 Hz, executing the latent plan made by System 2. We deploy N1 on GR1 robot, 1X Neo robot, and a large collection of simulation benchmarks. N1 achieves up to +30% boost in diverse manipulation tasks for household and industrial settings. While humanoid robots are the main focus of N1, our model also supports cross-embodiment. We finetune it to work on the $110 HuggingFace LeRobot SO100 robot arm! Open robot brain runs on open hardware. Sounds just right. Let’s solve robotics, together, one token at a time. Links to our Whitepaper, Github repo, HuggingFace model, and open dataset page in the thread: 🧵
2:21

Excited to announce GR00T N1, the world’s first open foundation model for humanoid robots! We are on a mission to democratize Physical AI. The power of general robot brain, in the palm of your hand - with only 2B parameters, N1 learns from the most diverse physical action dataset ever compiled and punches above its weight: - Real humanoid teleoperation data. - Large-scale simulation data: we are open-sourcing 300K+ trajectories! - Neural trajectories: we apply SOTA video generation models to “hallucinate” new synthetic data that features accurate physics in pixels. Using Jensen’s words, “systematically infinite data”! - Latent actions: we develop novel algorithms to extract action tokens from in-the-wild human videos and neural generated videos. GR00T N1 is a single end-to-end neural net, from photons to actions: - Vision-Language Model (System 2) that interprets the physical world through vision and language instructions, enabling robots to reason about their environment and instructions, and plan the right actions. - Diffusion Transformer (System 1) that “renders” smooth and precise motor actions at 120 Hz, executing the latent plan made by System 2. We deploy N1 on GR1 robot, 1X Neo robot, and a large collection of simulation benchmarks. N1 achieves up to +30% boost in diverse manipulation tasks for household and industrial settings. While humanoid robots are the main focus of N1, our model also supports cross-embodiment. We finetune it to work on the $110 HuggingFace LeRobot SO100 robot arm! Open robot brain runs on open hardware. Sounds just right. Let’s solve robotics, together, one token at a time. Links to our Whitepaper, Github repo, HuggingFace model, and open dataset page in the thread: 🧵

Jim Fan

467,416 просмотров • 1 год назад